EUVIMEDEUVIMED entdecken
Crossref

Knowledge‐Guided Multi‐Agent Framework for Metasurface Design Automation

Yan Zhang, Xuan Zheng, Shi Long Qin, Long Chen, Zi Xuan Cai, Jian Lin Su, Shan Shan Wang, Yu Shan Liu, Ping Rong, Jia Teng Wu, Yi Chen Yang, Tie Jun Cui und 1 weitere

Advanced Functional Materials · 13.11.2026

DOI: 10.1002/adfm.79267 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Functional Materials, online erschienen am 13.11.2026. Verfasst von Yan Zhang und 12 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Higher Education Discipline Innovation Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Inverse design of electromagnetic metasurface plays a pivotal role in tailoring subwavelength structures to achieve specific wavefront manipulations and exotic functionalities. The design of metasurface typically begins with finding a proper structure prototype according to user demand, requiring domain experts to take considerable time for literature retrieval and filtering. Recently, large language models (LLMs) pave a promising way for research automation, owing to its capability of knowledge query, step‐by‐step reasoning, and on‐demand tool calling. Here, we propose MetaChatAgent, an LLM‐assisted toolbox empowered by multi‐agent collaboration and retrieval‐augmented generation. It integrates three specialized agents to replace labor‐intensive research processes. A data‐analysis agent is firstly developed to execute the holistic literature mining from semantic knowledge databases, enabling human‐free data mining and feature analysis. Next, a retrieval‐reasoning agent is presented to retrieve the relevant knowledge in the vast literature according to user demand, whose effectiveness is validated by a query‐answer benchmark of metasurfaces across various scenarios. Finally, a reproduction agent is proposed to automatically reconstruct the parametric structure of metasurface and conduct the property reproduction facilitated by specialized simulation tools. This work establishes a knowledge‐guided multi‐agent framework for AI‐in‐the‐loop metasurface research, automating tasks including literature mining, evidence‐grounded analysis, structural reconstruction, and simulation‐based validation.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Higher Education Discipline Innovation Project

Zitieren

APA

Zhang, Y., Zheng, X., Qin, S. L., Chen, L., Cai, Z. X., Su, J. L., Wang, S. S., Liu, Y. S., Rong, P., Wu, J. T., Yang, Y. C., Cui, T. J., & You, J. W. (2026). Knowledge‐Guided Multi‐Agent Framework for Metasurface Design Automation. Advanced Functional Materials. https://doi.org/10.1002/adfm.79267

Vancouver

Zhang Y, Zheng X, Qin SL, Chen L, Cai ZX, Su JL, et al. Knowledge‐Guided Multi‐Agent Framework for Metasurface Design Automation. Advanced Functional Materials. 2026. doi:10.1002/adfm.79267

BibTeX
@article{Zhang2026,
  author = {Zhang, Yan and Zheng, Xuan and Qin, Shi Long and Chen, Long and Cai, Zi Xuan and Su, Jian Lin and Wang, Shan Shan and Liu, Yu Shan and Rong, Ping and Wu, Jia Teng and Yang, Yi Chen and Cui, Tie Jun and You, Jian Wei},
  title = {Knowledge‐Guided Multi‐Agent Framework for Metasurface Design Automation},
  journal = {Advanced Functional Materials},
  year = {2026},
  doi = {10.1002/adfm.79267}
}
Kostenlos starten →